Upload LlamaForCausalLM (#1)

- Upload LlamaForCausalLM (dc80f4ca32409f0defc08f61e1fe71d0b72d5265)
- Upload LlamaForCausalLM (0b4902cce3aef0d5925aeb25a90a557c89f31ece)
- Upload LlamaForCausalLM (19fca54708332562489f1c6a19d8b3d54b7222d1)
- Upload LlamaForCausalLM (66f832b39f986650966ba6fe4b18c19d7d952ff7)
- Upload LlamaForCausalLM (cd6fe1c5e7dfc3e2cbb94aa6207ab09a3e93ccf5)
- Upload LlamaForCausalLM (3b2319d044f76ca056bf9dda71e183a761d0aafc)


Co-authored-by: Joshua <[email protected]>

config.json

@@ -1,35 +1,34 @@
-{
-  "architectures": [
-    "LlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "head_dim": 64,
-  "hidden_act": "silu",
-  "hidden_size": 1024,
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "max_position_embeddings": 131072,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 30,
-  "num_key_value_heads": 16,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 8.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
-  },
-  "rope_theta": 500000.0,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
-  "use_cache": true,
-  "vocab_size": 8194
-}
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 16,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 8194
+}

generation_config.json

@@ -1,6 +1,6 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "transformers_version": "4.46.3"
-}
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a38e0b8413390f16c0d00cdd9b89c7a646ccfba8c6b975059e24fe186e96977f
-size 2047109432
+oid sha256:65943be5ae92ed7f80951b9ccbc9db8042931ff7b6915c9de071c58d6e933408
+size 2080672160